Repository navigation
chore: bump mlx-swift for compiled kernel dtype fix - #193
Merged
Merged
Conversation
Picks up SharpAI/mlx-swift#19: compiled kernel names now include the input dtypes, so graphs that differ only in input dtype no longer share one Metal library. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Bumps
mlx-swiftfrom 384de38 to 1a2b3af to pick up SharpAI/mlx-swift#19 (the only change in that range). Compiled kernel names now include the input dtypes. Before, two graphs that differed only in input dtype (for example bf16 and f16) shared one Metal library, so the second graph ran the first graph's kernel. This is the upstream fix ml-explore/mlx#3427, applied ahead of the upstream sync.mlx-swift-lmis unchanged (7cc37a0).Tested on M5 Pro:
swift build -c releaseandswift build --build-testsSwiftLMTests: 194 tests, 0 failuresSwiftBuddyTests: 127 tests, 9 skipped, 0 failuresmlx-community/Qwen3.5-0.8B-4bit --turbo-kv: single-turn and multi-turn chat answer correctly. Without--turbo-kv, text requests to this model fail withunsupportedBatchContinuationon main as well. That is a separate issue and not related to this bump.AI usage: Claude Code (Claude Opus 5.5) made the bump, ran the tests and wrote this description.
🤖 Generated with Claude Code